clocksource: Make watchdog robust vs. interruption

commit b5199515c25cca622495eb9c6a8a1d275e775088 upstream.

The clocksource watchdog code is interruptible and it has been
observed that this can trigger false positives which disable the TSC.

The reason is that an interrupt storm or a long running interrupt
handler between the read of the watchdog source and the read of the
TSC brings the two far enough apart that the delta is larger than the
unstable treshold. Move both reads into a short interrupt disabled
region to avoid that.

Reported-and-tested-by: Vernon Mauery <vernux@us.ibm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index f73bc1b68c107d9d68531de46ad916d18de070c3..ca5c0c495aa7f44973dfaacffe98a367caaa93fd 100644 (file)
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -190,6 +190,7 @@ struct clocksource {
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
        /* Watchdog related data, used by the framework */
        struct list_head wd_list;
+       cycle_t cs_last;
        cycle_t wd_last;
 #endif
 };

diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index bf4fe98bcba8b4f16c9f4db35a9fb471c7c18660..a02e070dfedc391903c76b1c1994cabed6cc15c1 100644 (file)
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -131,7 +131,6 @@ static struct clocksource *watchdog;
 static struct timer_list watchdog_timer;
 static DECLARE_WORK(watchdog_work, clocksource_watchdog_work);
 static DEFINE_SPINLOCK(watchdog_lock);
-static cycle_t watchdog_last;
 static int watchdog_running;
 
 static int clocksource_watchdog_kthread(void *data);
@@ -200,11 +199,6 @@ static void clocksource_watchdog(unsigned long data)
        if (!watchdog_running)
                goto out;
 
-       wdnow = watchdog->read(watchdog);
-       wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask,
-                                    watchdog->mult, watchdog->shift);
-       watchdog_last = wdnow;
-
        list_for_each_entry(cs, &watchdog_list, wd_list) {
 
                /* Clocksource already marked unstable? */
@@ -214,19 +208,28 @@ static void clocksource_watchdog(unsigned long data)
                        continue;
                }
 
+               local_irq_disable();
                csnow = cs->read(cs);
+               wdnow = watchdog->read(watchdog);
+               local_irq_enable();
 
                /* Clocksource initialized ? */
                if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) {
                        cs->flags |= CLOCK_SOURCE_WATCHDOG;
-                       cs->wd_last = csnow;
+                       cs->wd_last = wdnow;
+                       cs->cs_last = csnow;
                        continue;
                }
 
-               /* Check the deviation from the watchdog clocksource. */
-               cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) &
+               wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask,
+                                            watchdog->mult, watchdog->shift);
+
+               cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) &
                                             cs->mask, cs->mult, cs->shift);
-               cs->wd_last = csnow;
+               cs->cs_last = csnow;
+               cs->wd_last = wdnow;
+
+               /* Check the deviation from the watchdog clocksource. */
                if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
                        clocksource_unstable(cs, cs_nsec - wd_nsec);
                        continue;
@@ -264,7 +267,6 @@ static inline void clocksource_start_watchdog(void)
                return;
        init_timer(&watchdog_timer);
        watchdog_timer.function = clocksource_watchdog;
-       watchdog_last = watchdog->read(watchdog);
        watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL;
        add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask));
        watchdog_running = 1;